Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5178 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0289. Min Range: -6.0289
Max Act: 6.0289. Min Act: -0.1700
Data Index: 1910434 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0289. Min Range: -6.0289
Max Act: 5.9352. Min Act: -0.1700
Data Index: 6645276 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0289. Min Range: -6.0289
Max Act: 5.8102. Min Act: -0.1700
Data Index: 7908363 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0289. Min Range: -6.0289
Max Act: 5.6852. Min Act: -0.1699
Data Index: 1039842 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0289. Min Range: -6.0289
Max Act: 5.6852. Min Act: -0.1700
Data Index: 8014202 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0289. Min Range: -6.0289
Max Act: 5.6539. Min Act: -0.1700
Data Index: 7267072 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0289. Min Range: -6.0289
Max Act: 5.6227. Min Act: -0.1700
Data Index: 5728241 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0289. Min Range: -6.0289
Max Act: 5.6227. Min Act: -0.1700
Data Index: 2473945 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0289. Min Range: -6.0289
Max Act: 5.5914. Min Act: -0.1700
Data Index: 6464134 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0289. Min Range: -6.0289
Max Act: 5.5914. Min Act: -0.1700
Data Index: 2934921 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0289. Min Range: -6.0289
Max Act: 5.5914. Min Act: -0.1700
Data Index: 6406075 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0289. Min Range: -6.0289
Max Act: 5.5914. Min Act: -0.1700
Data Index: 7846024 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0289. Min Range: -6.0289
Max Act: 5.5602. Min Act: -0.1700
Data Index: 1865559 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0289. Min Range: -6.0289
Max Act: 5.5602. Min Act: -0.1700
Data Index: 6684597 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0289. Min Range: -6.0289
Max Act: 5.5289. Min Act: -0.1700
Data Index: 4054383 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0289. Min Range: -6.0289
Max Act: 5.5289. Min Act: -0.1699
Data Index: 6005970 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0289. Min Range: -6.0289
Max Act: 5.5602. Min Act: -0.1700
Data Index: 7592918 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0289. Min Range: -6.0289
Max Act: 5.4664. Min Act: -0.1700
Data Index: 5962904 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0289. Min Range: -6.0289
Max Act: 5.4977. Min Act: -0.1700
Data Index: 5499436 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0289. Min Range: -6.0289
Max Act: 5.4664. Min Act: -0.1700
Data Index: 661889 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19